A new AI tool distinguishes Ewing sarcoma from similar tumors
A team from the Universitat Politècnica de València (UPV) and the University of Valencia (UV) has developed and validated an artificial intelligence (AI) system capable of distinguishing Ewing sarcoma from other morphologically similar tumors with high accuracy. The model, which also enables optimal use of biopsy tissue, achieves 91.6% accuracy.
A team from the Universitat Politècnica de València and the University of Valencia has created an artificial intelligence system capable of accurately distinguishing Ewing sarcoma from other tumors that appear similar under a microscope. This tool, the first of its kind, achieves a remarkable 91.6% accuracy rate. In diagnosing Ewing sarcoma, a rare pediatric and juvenile cancer, pathologists often face challenges as the tumor can be very similar to other soft tissue tumors such as rhabdomyosarcoma, chondrosarcoma, gastrointestinal stromal tumors, and synovial sarcoma.
The AI system reduces errors, saves scarce biopsy tissue, and guides the selection of necessary follow-up tests, thereby aiding pathologists in complex diagnoses. The model was trained on 1,926 digitized histological samples from 729 patients, including 517 cases of Ewing sarcoma. While the system does not replace pathologists, it provides valuable objective support, especially in hospitals with limited access to advanced molecular tests.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
